Online learning of linear predictors for real-time tracking

Authors:
Stefan Holzer;Marc Pollefeys;Slobodan Ilic;David Joseph Tan;Nassir Navab
Affiliations:
Department of Computer Science, Technische Universität München (TUM), Garching, Germany;Department of Computer Science, ETH Zurich, Zurich, Switzerland;Department of Computer Science, Technische Universität München (TUM), Garching, Germany;Department of Computer Science, Technische Universität München (TUM), Garching, Germany;Department of Computer Science, Technische Universität München (TUM), Garching, Germany
Venue:
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Year:
2012

Citing 10
Cited 1

Efficient Region Tracking With Parametric Models of Geometry and Illumination

IEEE Transactions on Pattern Analysis and Machine Intelligence
Systems and Experiment Paper: Construction of Panoramic Image Mosaics with Global and Local Alignment

International Journal of Computer Vision
Hyperplane Approximation for Template Matching

IEEE Transactions on Pattern Analysis and Machine Intelligence
Lucas-Kanade 20 Years On: A Unifying Framework

International Journal of Computer Vision
Homography-based 2D Visual Tracking and Servoing

International Journal of Robotics Research
Tracking with general regression

Machine Vision and Applications
Selection of Reliable Features Subsets for Appearance-Based Tracking

SITIS '07 Proceedings of the 2007 Third International IEEE Conference on Signal-Image Technologies and Internet-Based System
Tracking by an Optimal Sequence of Linear Predictors

IEEE Transactions on Pattern Analysis and Machine Intelligence
An iterative image registration technique with an application to stereo vision

IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Learning efficient linear predictors for motion estimation

ICVGIP'06 Proceedings of the 5th Indian conference on Computer Vision, Graphics and Image Processing

Multi-Target Tracking by Online Learning a CRF Model of Appearance and Motion Patterns

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

Although fast and reliable, real-time template tracking using linear predictors requires a long training time. The lack of the ability to learn new templates online prevents their use in applications that require fast learning. This especially holds for applications where the scene is not known a priori and multiple templates have to be added online. So far, linear predictors had to be either learned offline [1] or in an iterative manner by starting with a small sized template and growing it over time [2]. In this paper, we propose a fast and simple reformulation of the learning procedure that allows learning new linear predictors online.